- Research Article
- 10.63665/rh.v7i2.73
Empowering Security in IoT: Spring Search Algorithm with Optimal Machine Learning Enabled Intrusion Detection
- Jan 01, 2026
- Research Hub
- Manisha Kumari
Devices, sensors, and physical items are all part of what is known as the Internet of Things (IoT) embedded with technology that allows them to gather, exchange, and act upon information without human intervention. Security in IoT is essential to secure sensitive information, safeguard interconnected networks and devices from cyberattacks, and ensure the trustworthiness and reliability of IoT environment, thereby alleviating risks of privacy breaches, potential physical harm, and financial losses. IoT security includes authentication, encryption, access control, and intrusion detection measures to alleviate security attacks and protect against potential vulnerabilities. One efficient method of addressing security concerns in an Internet of Things (IoT) setting is to implement a system for intrusion detection (IDS), which employs ML and DL approaches to fortify protections. Therefore, this study introduces a new Spring Search Algorithm based on Feature Selection with Optimal Machine Learning Empowered Intrusion Detection (SSAFS-OMLID) in IoT framework. The projected SSAFS-OMLID model intends to detect the occurrence and recognition of intrusions in the IoT framework. Data pre-processing is the first step in preparing the data for analysis. After the data has been pre-processed, the SSAFS model is employed to pick features. Then, hop field neural network (HNN) classifier is exploited for the intrusion detection in the network. Finally, Sooty Tern Optimization Algorithm (STOA) is utilized to effectually adjust the parameters included in the HNN performance. In order to prove that the SSAFS-OMLID method is the best, researchers conducted extensive experiments, and the results showed that the method is very efficient according to several criteria.
Read more